Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Code and technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    weapon
    -0.07
    atchewan
    -0.07
    나라
    -0.06
     introduction
    -0.06
    lerdi
    -0.06
     datab
    -0.06
    embali
    -0.06
    _z
    -0.06
    .getInteger
    -0.06
    ्
    -0.06
    POSITIVE LOGITS
    .cert
    0.08
     rtl
    0.07
     createStore
    0.07
    /TR
    0.06
     emergence
    0.06
     manière
    0.06
    LANGUAGE
    0.06
    dete
    0.06
    Arrange
    0.06
    刊
    0.06
    Act Density 0.000%

    No Known Activations